/* Grid World v. 0.2
 * Author: Carlo Comin carlo.comin@studenti.unimi.it
 * 
 * This code is released under GPL3
 * 
 *  Date: Sept 29 2010 5:06pm
 * */

import java.awt.EventQueue;
import javax.swing.JFrame;
import javax.swing.JOptionPane;
import javax.swing.JTable;
import javax.swing.JScrollPane;
import javax.swing.JButton;
import java.awt.event.ActionListener;
import java.awt.event.ActionEvent;
import javax.swing.JTextField;
import javax.swing.JLabel;
import javax.swing.Box;
import javax.swing.JTextPane;
import java.awt.Font;

public class GridWorld {

	private Integer gridsize;
	
	private JFrame frame;
	private static JTable table;
	private JTable table2;
	private JTextField textField;

	/**
	 * Launch the application.
	 */
	public static void main(String[] args) {
		EventQueue.invokeLater(new Runnable() {
			public void run() {
				try {
					GridWorld window = new GridWorld();
					window.frame.setVisible(true);
				} catch (Exception e) {
					e.printStackTrace();
				}
			}
		});
	}

	/**
	 * Create the application.
	 */
	public GridWorld() {
		initialize();
	}

	/**
	 * Initialize the contents of the frame.
	 */
	private void initialize() {
		frame = new JFrame();
		frame.setBounds(100, 100, 800, 600);
		frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
		frame.getContentPane().setLayout(null);
		
		final JScrollPane scrollPane = new JScrollPane();
		scrollPane.setBounds(276, 10, 514, 263);
		frame.getContentPane().add(scrollPane);
		
		final JScrollPane scrollPane_1 = new JScrollPane();
		scrollPane_1.setBounds(276, 305, 514, 263);
		frame.getContentPane().add(scrollPane_1);
		
		textField = new JTextField();
		gridsize = new Integer(5);
		textField.setText(Integer.toString(gridsize));
		textField.setBounds(77, 57, 67, 22);
		frame.getContentPane().add(textField);
		textField.setColumns(10);
		
		final JButton btnPolicy = new JButton("Compute Policy");
		btnPolicy.addActionListener(new ActionListener() {
			public void actionPerformed(ActionEvent argo0) {
				if(!checkInputOK())
					JOptionPane.showMessageDialog(frame, 
							"Insert at least one terminal state.");
				else{
					Object[][] rewardTable = getRewardTable();
					Object[][] policyTable = ValueIteration(rewardTable);
				
					String[] columnNames = new String[gridsize]; 
					for(int i=0; i < gridsize; i++) columnNames[i] = "";
					table2 = new JTable(policyTable, columnNames);
					table2.setAutoResizeMode(JTable.AUTO_RESIZE_OFF);
					scrollPane_1.setViewportView(table2);		
				}
			}
		});
		btnPolicy.setEnabled(false);
		btnPolicy.setBounds(140, 305, 130, 29);
		frame.getContentPane().add(btnPolicy);
		
		JButton btnCreate = new JButton("Create Grid");
		btnCreate.addActionListener(new ActionListener() {
			public void actionPerformed(ActionEvent arg0) {
				gridsize = Integer.parseInt(textField.getText());
				
				String[] columnNames = new String[gridsize];
				Object[][] data = new Object[gridsize][gridsize];
				for(int i=0; i < gridsize; i++){
					columnNames[i] = "";
					for(int j=0; j < gridsize; j++)
						data[i][j] = "*";
				}
				
				table = new JTable(data,columnNames);
				table.setAutoResizeMode(JTable.AUTO_RESIZE_OFF);
				scrollPane.setViewportView(table);

				btnPolicy.setEnabled(true);				
			}
		});
		
		Box verticalBox = Box.createVerticalBox();
		verticalBox.setBounds(0, 0, 1, 1);
		frame.getContentPane().add(verticalBox);
		btnCreate.setBounds(169, 53, 101, 29);
		frame.getContentPane().add(btnCreate);
		
		JLabel lblGridSize = new JLabel("Grid Size");
		lblGridSize.setBounds(10, 60, 61, 16);
		frame.getContentPane().add(lblGridSize);
		
		JLabel lblGridWorld = new JLabel("Grid World 0.2");
		lblGridWorld.setBounds(10, 10, 90, 22);
		frame.getContentPane().add(lblGridWorld);
		
		JLabel lblByCarlocharlie = new JLabel("by Charlie #754846");
		lblByCarlocharlie.setBounds(106, 13, 164, 16);
		frame.getContentPane().add(lblByCarlocharlie);
		
		JTextPane txtpnGridCellLegend = new JTextPane();
		txtpnGridCellLegend.setEnabled(false);
		txtpnGridCellLegend.setFont(new Font("Lucida Grande", Font.PLAIN, 14));
		txtpnGridCellLegend.setEditable(false);
		txtpnGridCellLegend.setText("Grid Cell Legend\r* = Normal cell\rT = Terminal cell\rO = Obstacle cell\r\rYou can add as many Terminal and Obstacles cells as you want.\rThen click Compute Policy.\rEnjoy!");
		txtpnGridCellLegend.setBounds(23, 96, 232, 159);
		frame.getContentPane().add(txtpnGridCellLegend);
		
		JTextPane txtpnPolicyLegendL = new JTextPane();
		txtpnPolicyLegendL.setEnabled(false);
		txtpnPolicyLegendL.setText("Policy Legend\rL = Left\tR = Right\rU = Up\tD = Down\rT = Terminal O = Obstacle");
		txtpnPolicyLegendL.setEditable(false);
		txtpnPolicyLegendL.setBounds(23, 349, 232, 72);
		frame.getContentPane().add(txtpnPolicyLegendL);
	}

	private Object[][] getRewardTable(){
		Object [][] ret = new Object[gridsize][gridsize];
		
		for(int i=0; i < gridsize; i++){
			for(int j=0; j < gridsize; j++){
				String val = (String)table.getValueAt(i, j);
				if(val.matches("O")||val.matches("o")) ret[i][j] = new Integer(-10000);
				else ret[i][j]= new Integer(-1);
			}
		}
		
		return ret;
	}
	
	private int reward(int i, int j, Object [][] rewardTable){
		int ret = (Integer)rewardTable[i][j];
		return ret;
	}
	
	private int UpdatedValue(int i, int j, int [][] Value, Object [][] rewardTable){
		String temp = (String)table.getValueAt(i, j);
		if(temp.matches("T")||temp.matches("t")){ 
			return 0;
		}
		
		int max=-32000;
		
		/* action:	code	meaning
		 * 			0		left
		 * 			1		right
		 * 			2		up
		 * 			3		down
		 * */
		for(int action=0; action < 4; action++){
			int next_i=i, next_j=j;
			if(action==0 && j!=0) { next_i=i; next_j=j-1; }
			else if(action==1 && j!=gridsize-1){ next_i=i; next_j=j+1; }
			else if(action==2 && i!=0){ next_i=i-1; next_j=j; }
			else if(action==3 && i!=gridsize-1){ next_i=i+1; next_j=j; }
			 
			 max=Math.max(max, reward(next_i, next_j, getRewardTable()) + Value[next_i][next_j]);
		}
		
		return max;
	}
	
	private Object [][] ComputePolicy(int [][] Value, Object [][] rewardTable){
		Object [][] policy = new Object[gridsize][gridsize];
		for(int i=0; i < gridsize; i++)
			for(int j=0; j < gridsize; j++){		
				String temp = (String)table.getValueAt(i, j);
				if(temp.matches("T")||temp.matches("t")) policy[i][j]="T";
				else if(temp.matches("O")||temp.matches("o")) policy[i][j]="O";
				else{
					int max=-32000;
					int oldmax=max, next_i,next_j;
					String action="L"; next_i=i; next_j=j;
					
					if(j!=0) { next_i=i; next_j=j-1; }
						 max=reward(next_i, next_j, getRewardTable()) + Value[next_i][next_j];
						 if(max>oldmax) policy[i][j]=action;
						 if(max==oldmax) policy[i][j] = policy[i][j] + " " + action;
						 if(max<oldmax) max=oldmax;
						 
					oldmax=max;
					action="R"; next_i=i; next_j=j;
					if(j!=gridsize-1) { next_i=i; next_j=j+1; }
						max=reward(next_i, next_j, getRewardTable()) + Value[next_i][next_j];
					 	if(max>oldmax) policy[i][j]=action;
					 	if(max==oldmax) policy[i][j] = policy[i][j] + " " + action;
					 	if(max<oldmax) max=oldmax;
					 	
					 oldmax=max;
					 	action="U"; next_i=i; next_j=j;
						if(i!=0) { next_i=i-1; next_j=j; }
							max=reward(next_i, next_j, getRewardTable()) + Value[next_i][next_j];
						 	if(max>oldmax) policy[i][j]=action;
						 	if(max==oldmax) policy[i][j] = policy[i][j] + " " + action;
						 	if(max<oldmax) max=oldmax;
					
						 	oldmax=max;
						 	action="D"; next_i=i; next_j=j;
							if(i!=gridsize-1) { next_i=i+1; next_j=j; }
								max=reward(next_i, next_j, getRewardTable()) + Value[next_i][next_j];
							 	if(max>oldmax) policy[i][j]=action;
							 	if(max==oldmax) policy[i][j] = policy[i][j] + " " + action;
							 	if(max<oldmax) max=oldmax;
				}
			}
		return policy;
	}
	
	private Object [][] ValueIteration(Object[][] rewardTable){
		int [][] Value = new int[gridsize][gridsize]; //Value function
		float delta, tetha;
		
		//init V(s) := 0
		for(int i=0; i < gridsize; i++)
			for(int j=0; j < gridsize; j++)
				Value[i][j]=0;
		
		tetha=0.1f;
		
		do{
			delta = 0;
			for(int i = 0; i< gridsize; i++)
				for(int j=0; j< gridsize; j++){
					int v=Value[i][j];
					Value[i][j] = UpdatedValue(i, j, Value, getRewardTable());
					delta = Math.max(delta, Math.abs(v-Value[i][j]));
				}
		}while(delta > tetha);
		
		return ComputePolicy(Value, rewardTable);
	} 
	
	private boolean checkInputOK(){
		for(int i=0; i<gridsize; i++)
			for(int j=0;j<gridsize; j++)
				if (((String) (table.getValueAt(i, j))).matches("T")) return true;
		return false;
	}
}